AggMapNet: enhanced and explainable low-sample omics deep learning with feature-aggregated multi-channel networks.

Abstract

Omics-based biomedical learning frequently relies on data of high-dimensions (up to thousands) and low-sample sizes (dozens to hundreds), which challenges efficient deep learning (DL) algorithms, particularly for low-sample omics investigations. Here, an unsupervised novel feature aggregation tool AggMap was developed to Aggregate and Map omics features into multi-channel 2D spatial-correlated image-like feature maps (Fmaps) based on their intrinsic correlations. AggMap exhibits strong feature reconstruction capabilities on a randomized benchmark dataset, outperforming existing methods. With AggMap multi-channel Fmaps as inputs, newly-developed multi-channel DL AggMapNet models outperformed the state-of-the-art machine learning models on 18 low-sample omics benchmark tasks. AggMapNet exhibited better robustness in learning noisy data and disease classification. The AggMapNet explainable module Simply-explainer identified key metabolites and proteins for COVID-19 detections and severity predictions. The unsupervised AggMap algorithm of good feature restructuring abilities combined with supervised explainable AggMapNet architecture establish a pipeline for enhanced learning and interpretability of low-sample omics data.

• Authors: Wan Xiang Shen, Yu Liu, Yan Chen, Xian Zeng, Ying Tan, Yu Yang Jiang, Yu Zong Chen
• Journal: Nucleic acids research (Nucleic Acids Res) Vol. 50 Issue 8 Pg. e45 (05 06 2022) ISSN: 1362-4962 [Electronic] England
• PMID: 35100418 (Publication Type: Journal Article, Research Support, Non-U.S. Gov't)
• Copyright: © The Author(s) 2022. Published by Oxford University Press on behalf of Nucleic Acids Research.

Chemical References

• Proteins

Topics

• Algorithms
• COVID-19
• Deep Learning
• Humans
• Machine Learning
• Proteins